{"jtbd":{"id":"budget-open-inference","slug":"budget-open-inference","name":"Ultra-budget open-model inference","shortName":"Ultra-budget open-model inference"},"recommended":{"role":"depot_pick","id":"deepinfra","slug":"deepinfra","name":"DeepInfra","website":"https://deepinfra.com","editorialOverall":7.95,"scoreKind":"curated_estimate","scoreAsOf":"2026-09-14","price":{"available":true,"unavailableReason":null,"skus":[{"id":"deepinfra-bge-base-en","providerId":"deepinfra","sku":"bge-base-en-v1.5","unit":"usd_per_million_input_tokens","amountUsd":0.005,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.005,"normalizationReason":"embedding_sku_excluded_from_provider_sort","priceSortEligible":false,"qualifier":"embeddings; input only","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":0,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"deepinfra-llama-33-70b-turbo-input","providerId":"deepinfra","sku":"Llama-3.3-70B-Instruct-Turbo","unit":"usd_per_million_input_tokens","amountUsd":0.1,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.1,"normalizationReason":null,"priceSortEligible":true,"qualifier":"128k context row","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":0,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"deepinfra-llama-33-70b-turbo-output","providerId":"deepinfra","sku":"Llama-3.3-70B-Instruct-Turbo","unit":"usd_per_million_output_tokens","amountUsd":0.32,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.32,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":null,"verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":0,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"deepinfra-gpu-a100","providerId":"deepinfra","sku":"A100","unit":"usd_per_gpu_hour","amountUsd":1.49,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-20","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"dedicated GPU-hour","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":0,"stale":false,"firstSeen":"2026-10-03","lastChanged":"2026-10-20","frequentlyChanging":false},{"id":"deepinfra-gpu-b200","providerId":"deepinfra","sku":"B200","unit":"usd_per_gpu_hour","amountUsd":4.89,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-20","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"dedicated GPU-hour","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":0,"stale":false,"firstSeen":"2026-10-03","lastChanged":"2026-10-20","frequentlyChanging":false},{"id":"deepinfra-gpu-b300","providerId":"deepinfra","sku":"B300","unit":"usd_per_gpu_hour","amountUsd":5.89,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-20","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"dedicated GPU-hour","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":0,"stale":false,"firstSeen":"2026-10-03","lastChanged":"2026-10-20","frequentlyChanging":false},{"id":"deepinfra-gpu-h100","providerId":"deepinfra","sku":"H100","unit":"usd_per_gpu_hour","amountUsd":2.9,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-20","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"dedicated GPU-hour","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":0,"stale":false,"firstSeen":"2026-10-03","lastChanged":"2026-10-20","frequentlyChanging":false},{"id":"deepinfra-gpu-h200","providerId":"deepinfra","sku":"H200","unit":"usd_per_gpu_hour","amountUsd":3.49,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-20","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"dedicated GPU-hour","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":0,"stale":false,"firstSeen":"2026-10-03","lastChanged":"2026-10-20","frequentlyChanging":false}],"normalizedUsdPerMillionTokens":null,"normalizationStatus":"ambiguous","normalizationReason":"input_output_split_not_a_single_rate"}},"priceComparison":{"skuKind":"chat_completion_input","unit":"usd_per_million_input_tokens","comparison":"min sourced input SKU among candidates; not quality-adjusted","amountLabel":"Input $/1M","reportsUsdPerMillion":true,"matchedCandidates":4},"cheapestInput":{"providerId":"chutes","slug":"chutes","name":"Chutes","skuId":"chutes-qwen3-8-27b-qwen-qwen3-8-27b-tee-in","item":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE)","plan":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE) — Public TEE inference, USD per 1M tokens","isFloorPrice":true,"floorWarning":"Provider-wide floor SKU; may not be the flagship model scored for this JTBD.","skuKind":"chat_completion_input","unit":"usd_per_million_input_tokens","comparison":"min sourced input SKU among candidates; not quality-adjusted","amountUsd":0.039,"usdPerMillionInputTokens":0.039,"sku":{"id":"chutes-qwen3-8-27b-qwen-qwen3-8-27b-tee-in","providerId":"chutes","sku":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.039,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.039,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored.","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed_manual","ageDays":0,"stale":false,"firstSeen":"2026-10-03","lastChanged":"2026-10-19","frequentlyChanging":false},"tiedWith":[]},"cheapest":{"providerId":"chutes","slug":"chutes","name":"Chutes","skuId":"chutes-qwen3-8-27b-qwen-qwen3-8-27b-tee-in","item":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE)","plan":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE) — Public TEE inference, USD per 1M tokens","isFloorPrice":true,"floorWarning":"Provider-wide floor SKU; may not be the flagship model scored for this JTBD.","skuKind":"chat_completion_input","unit":"usd_per_million_input_tokens","comparison":"min sourced input SKU among candidates; not quality-adjusted","amountUsd":0.039,"usdPerMillionInputTokens":0.039,"sku":{"id":"chutes-qwen3-8-27b-qwen-qwen3-8-27b-tee-in","providerId":"chutes","sku":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.039,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.039,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored.","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed_manual","ageDays":0,"stale":false,"firstSeen":"2026-10-03","lastChanged":"2026-10-19","frequentlyChanging":false},"tiedWith":[]},"recommendedWorkloadQuote":{"providerId":"deepinfra","providerName":"DeepInfra","skuId":"deepinfra-bge-base-en","item":"bge-base-en-v1.5","plan":"bge-base-en-v1.5 — embeddings; input only","unit":"usd_per_million_input_tokens","amountUsd":0.005,"outputSkuId":null,"outputItem":null,"outputAmountUsd":null,"outputUnit":null,"sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-03","pricingLastVerifiedAt":"2026-10-27","isFlagshipForJob":false,"differsFromFloorCheapest":false,"representativeQuote":{"skuId":"deepinfra-bge-base-en","item":"bge-base-en-v1.5","plan":"bge-base-en-v1.5 — embeddings; input only","amountUsd":0.005,"inputOrUnitUsd":0.005,"unit":"usd_per_million_input_tokens","outputUsd":null,"outputUnit":null,"sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-03"},"estimatedTaskCost":{"tasks":1000,"retryAndToolOverheadMultiplier":1.15,"retryToolOverheadMultiplier":1.15,"inputTokensPerTask":4000,"outputTokensPerTask":0,"baseCostPer1kTasksUsd":0.02,"totalUsd":0.023,"estimatedTotalUsd":0.023,"perTaskUsd":0.000023,"estimatedCostPerTaskUsd":0.000023,"formula":"((4,000 tokens * $0.005/1M) * 1,000 tasks) * 1.15 overhead","assumptions":"1,000 agent tasks @ 4k input + 1k output tokens/task with 1.15x retry/tool-call overhead."}},"representativeQuote":{"skuId":"deepinfra-bge-base-en","item":"bge-base-en-v1.5","plan":"bge-base-en-v1.5 — embeddings; input only","amountUsd":0.005,"inputOrUnitUsd":0.005,"unit":"usd_per_million_input_tokens","outputUsd":null,"outputUnit":null,"sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-03"},"estimatedTaskCost":{"tasks":1000,"retryAndToolOverheadMultiplier":1.15,"retryToolOverheadMultiplier":1.15,"inputTokensPerTask":4000,"outputTokensPerTask":0,"baseCostPer1kTasksUsd":0.02,"totalUsd":0.023,"estimatedTotalUsd":0.023,"perTaskUsd":0.000023,"estimatedCostPerTaskUsd":0.000023,"formula":"((4,000 tokens * $0.005/1M) * 1,000 tasks) * 1.15 overhead","assumptions":"1,000 agent tasks @ 4k input + 1k output tokens/task with 1.15x retry/tool-call overhead."},"cheapestGoodEnough":{"band":{"rule":"editorial overall >= Depot Pick overall - 0.5","minOverall":7.45,"pickOverall":7.95,"points":0.5},"pick":{"providerId":"zai","slug":"zai","name":"Z.AI (Zhipu GLM)","skuId":"zai-glm-4-6v-flashx-in","item":"GLM-4.6V-FlashX","plan":"GLM-4.6V-FlashX — Prices per 1M tokens","isFloorPrice":true,"floorWarning":"Provider-wide floor SKU; may not be the flagship model scored for this JTBD.","skuKind":"chat_completion_input","unit":"usd_per_million_input_tokens","comparison":"min sourced input SKU among candidates; not quality-adjusted","amountUsd":0.04,"usdPerMillionInputTokens":0.04,"sku":{"id":"zai-glm-4-6v-flashx-in","providerId":"zai","sku":"GLM-4.6V-FlashX","unit":"usd_per_million_input_tokens","amountUsd":0.04,"currency":"USD","sourceUrl":"https://docs.z.ai/guides/overview/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.04,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Prices per 1M tokens. Cached input not folded in.","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":0,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},"tiedWith":[],"overall":7.79},"reason":null,"cheaperButBelowBand":[{"slug":"chutes","overall":7.29,"amountUsd":0.039}]},"dates":{"scoreAsOf":"2026-09-14","scoreKind":"curated_estimate","priceVerifiedAsOf":"2026-10-27","note":"scoreAsOf is when the editorial score was last set; priceVerifiedAsOf is the newest fact-check of the pick's price rows. They are separate: a fresh price check does not re-score."},"sourcedInputs":[{"providerId":"chutes","slug":"chutes","name":"Chutes","skuId":"chutes-qwen3-8-27b-qwen-qwen3-8-27b-tee-in","item":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE)","plan":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE) — Public TEE inference, USD per 1M tokens","isFloorPrice":true,"floorWarning":"Provider-wide floor SKU; may not be the flagship model scored for this JTBD.","skuKind":"chat_completion_input","unit":"usd_per_million_input_tokens","amountUsd":0.039,"usdPerMillionInputTokens":0.039,"sku":{"id":"chutes-qwen3-8-27b-qwen-qwen3-8-27b-tee-in","providerId":"chutes","sku":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE)","unit":"usd_per_million_input_tokens","amountUsd":0.039,"currency":"USD","sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.039,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Public TEE inference, USD per 1M tokens. Workload estimate on the same card was not used. TAO column not used. Reconfirmed 2026-10-27 (v0.12.141). The page says per-model rates are 'pulled live from our pricing API'; cached-input rate on the same card not stored.","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed_manual","ageDays":0,"stale":false,"firstSeen":"2026-10-03","lastChanged":"2026-10-19","frequentlyChanging":false},"isDepotPick":false},{"providerId":"zai","slug":"zai","name":"Z.AI (Zhipu GLM)","skuId":"zai-glm-4-6v-flashx-in","item":"GLM-4.6V-FlashX","plan":"GLM-4.6V-FlashX — Prices per 1M tokens","isFloorPrice":true,"floorWarning":"Provider-wide floor SKU; may not be the flagship model scored for this JTBD.","skuKind":"chat_completion_input","unit":"usd_per_million_input_tokens","amountUsd":0.04,"usdPerMillionInputTokens":0.04,"sku":{"id":"zai-glm-4-6v-flashx-in","providerId":"zai","sku":"GLM-4.6V-FlashX","unit":"usd_per_million_input_tokens","amountUsd":0.04,"currency":"USD","sourceUrl":"https://docs.z.ai/guides/overview/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.04,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Prices per 1M tokens. Cached input not folded in.","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":0,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},"isDepotPick":false},{"providerId":"deepinfra","slug":"deepinfra","name":"DeepInfra","skuId":"deepinfra-llama-33-70b-turbo-input","item":"Llama-3.3-70B-Instruct-Turbo","plan":"Llama-3.3-70B-Instruct-Turbo — 128k context row","isFloorPrice":true,"floorWarning":"Provider-wide floor SKU; may not be the flagship model scored for this JTBD.","skuKind":"chat_completion_input","unit":"usd_per_million_input_tokens","amountUsd":0.1,"usdPerMillionInputTokens":0.1,"sku":{"id":"deepinfra-llama-33-70b-turbo-input","providerId":"deepinfra","sku":"Llama-3.3-70B-Instruct-Turbo","unit":"usd_per_million_input_tokens","amountUsd":0.1,"currency":"USD","sourceUrl":"https://deepinfra.com/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.1,"normalizationReason":null,"priceSortEligible":true,"qualifier":"128k context row","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":0,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},"isDepotPick":true},{"providerId":"minimax","slug":"minimax","name":"MiniMax","skuId":"minimax-minimax-m3-1-flash-in","item":"MiniMax-M3.1-Flash","plan":"MiniMax-M3.1-Flash — Pay-as-you-go, USD per 1M tokens, from the LLM table of the official pricing page (Markdown twin)","isFloorPrice":true,"floorWarning":"Provider-wide floor SKU; may not be the flagship model scored for this JTBD.","skuKind":"chat_completion_input","unit":"usd_per_million_input_tokens","amountUsd":0.15,"usdPerMillionInputTokens":0.15,"sku":{"id":"minimax-minimax-m3-1-flash-in","providerId":"minimax","sku":"MiniMax-M3.1-Flash","unit":"usd_per_million_input_tokens","amountUsd":0.15,"currency":"USD","sourceUrl":"https://platform.minimax.io/docs/guides/pricing-paygo.md","asOf":"2026-10-19","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.15,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Pay-as-you-go, USD per 1M tokens, from the LLM table of the official pricing page (Markdown twin). Input.","verifiedAsOf":"2026-10-27","sourceCheck":"reconfirmed","ageDays":0,"stale":false,"firstSeen":"2026-10-19","lastChanged":null,"frequentlyChanging":false},"isDepotPick":false}],"pickIsPriceWinner":false,"priceWinnerReason":"pick_price_above_cheapest","priceWinnerNote":"Pick is not a price winner. deepinfra sourced input $/1M is 0.1; cheapest among candidates is chutes at 0.039.","excluded":4,"coverage":{"candidates":8,"withAnySourcedRow":4,"withSourcedInputUsdPerMillion":4,"withMatchingPrice":4,"excludedNoSourcedPrice":4,"excludedFromCheapestInput":4},"normalizedUsdPerMillionTokens":null,"normalizationReason":"input_and_output_are_not_blended","seo":{"published":true,"reason":"At least 3 candidates have a matching Input $/1M (chat_completion_input), so /jtbds/budget-open-inference includes a crawlable sourced-price section."},"cite":"Depot Pick for budget-open-inference: deepinfra (asOf 2026-09-14). See GET /api/jtbds/budget-open-inference + GET /api/methodology.","asOf":"2026-10-27","honesty":["Recommended provider is the current Depot Pick from GET /api/decide. This quote does not change scores.","SKU rows are copied from data/pricing-rows.json via GET /api/pricing. No new pages were scraped for this response.","normalizedUsdPerMillionTokens on this quote is always null. Input and output stay on separate rows.","cheapestInput compares one native unit that matches this job. Chat and coding jobs use priceSortEligible input $/1M. Embedding jobs use embedding SKUs only. Speech-to-text uses a stored speech unit only (per minute when that unit exists; a voice-agent hosting minute and a speech-engine minute are not speech-to-text). Speech synthesis uses one stored TTS unit in preference order (per minute, then per 1k characters, then per million characters) and does not mix those units or a speech-engine minute. Hosted-browser jobs compare usd_per_browser_hour only (lowest tier per provider, not quality-adjusted); proxy per GB, CAPTCHA solves, monthly plans, and chat tokens are not included. Sandbox, code-interpreter, ephemeral CI, and persistent dev env compare usd_per_vcpu_hour only, and only when the Depot Pick has that row; GPU-hour, GiB-hour, and vCPU-second are not converted. Secret jobs compare identity-month or user-month, never both; if both are stored, cheapestInput is null (mixed_secret_units). Voice-agent platform jobs compare a voice-agent hosting minute only. Transactional email compares usd_per_1k_emails only. Marketing email compares usd_per_1k_emails when a non-transactional per-1k SKU exists; otherwise it ranks a marketing-labeled usd_per_email and does not convert that rate to per 1k or mix it with per-1k. Monthly plans are not a unit price (plan_not_a_unit_price). Outbound and inbound webhook jobs compare usd_per_message only. Queue jobs compare usd_per_100k_messages or usd_per_million_events, never both (mixed_units). Push does not rank MAU or monthly plans. Error observability ranks a unit only when every candidate shares it; per-error fractions are not ranked against monthly plans. MotherDuck CU-hours and flight hours are not vCPU-hours. Composio's unsplit sandbox token rate is not chat $/1M. CAPTCHA SKUs are not ranked. Other non-token jobs do not borrow a chat $/1M rate. If nothing matches, cheapestInput is null.","excluded counts candidates with zero sourced pricing rows. excludedFromCheapestInput also counts candidates whose rows are a different unit than this job.","A Depot Pick is not a price winner unless its matching sourced price is the lowest among candidates. The comparison is not quality-adjusted. pickIsPriceWinner is null (not false) when nothing was compared."],"links":{"decide":"/api/decide?jtbd=budget-open-inference","quote":"/api/quote?jtbd=budget-open-inference","pricing":"/api/pricing?provider=deepinfra","leaderboardPrice":"/api/leaderboards?jtbd=budget-open-inference&sort=price","humanPage":"/jtbds/budget-open-inference#quote","methodology":"/api/methodology"},"sourceConflicts":[],"volumeEstimateHint":"Add &volume=<number> for a plan-level monthly cost (GET /api/estimate?jtbd=budget-open-inference&workload=...)"}